Bingxin Zhao, PhD Assistant Professor Department of Statistics and Data…
Haoyin Zhou, PhD
Instructor in Radiology
Department of Radiology
Brigham and Women’s Hospital
Harvard Medical School
Minimally invasive liver surgery (MILS) is the preferred treatment for liver tumors compared to traditional open surgery due to low blood loss, less patient trauma and faster postoperative recovery. Preoperatively, MILS is planned based on diagnostic MR/CT imaging, from which liver anatomical structures can be segmented accurately by using image-processing algorithms. However, preoperative data cannot be used intraoperatively because of liver deformation caused by carbon dioxide pneumoperitoneum, respiration and tissue manipulation. To solve this problem, we have employed the concept of simultaneous localization and mapping (SLAM) to reconstruct the 3D tissue surface from 2D laparoscopy images, and track the deformation in real-time. In this seminar, I will introduce a novel trackerless MILS navigation system, which was developed based on our non-rigid 3D reconstruction and registration methods. I will also discuss the potential of using deep learning methods to improve the accuracy and robustness of the surgical navigation system.
Haoyin is Instructor in Radiology at the Brigham and Women’s Hospital. He obtained his PhD in computer science from the Department of Automation, Tsinghua University. During his PhD, he conducted research in the broad area of vision-based navigation for robotics and autonomous driving problems. In 2016, he joined the surgical planning laboratory and works with Dr. Jayender Jagadeesan, since when he has been working in the interdisciplinary field of medicine and computer science. His research mainly focuses on developing novel computer vision methods for surgical navigation. He was awarded the NIH K99/R00 grant with the aim of developing a novel surgical navigation system for minimally invasive liver surgeries.